Geometry modeling of eyewear devices with flexible frames
An eyewear device with flexible frame for Augmented Reality (AR) is disclosed. At least two sensors and a display are mounted on the flexible frame. When in use, the real time geometry of the eyewear device may change from factory calibrated geometry, resulting in low quality AR rendering. A modeling module is provided to model the real time geometry of the eyewear device on the fly using sensor information of the at least two sensors. The modeled real time geometry is then provided to a rendering module to accurately display the AR to the user.
1. A system comprising:
an eyewear device for displaying augmented reality images, comprising:
an inertial measurement unit (IMU) that generates inertial data,
at least one image sensor that generates image data, and
at least one display for displaying the augmented reality images, wherein the eyewear device has a predetermined geometry defining spatial relations of at least two of the IMU, the at least one image sensor, or the at least one display; and
an augmented reality image rendering system including:
a motion tracking module that:
computes poses of the at least one image sensor and the IMU using at least the image data from the at least one image sensor and the inertial data from the IMU,
computes the predetermined geometry during use of the eyewear device in an augmented reality application, and
estimates an updated geometry of the eyewear device from the poses as a result of a geometry change of the eyewear device; and
a rendering module that renders the augmented reality images including virtual content and real-world objects on the at least one display in accordance with the estimated updated geometry.
2. The system of claim 1 , wherein the motion tracking module comprises a computer vision processing algorithm that computes poses of the at least one image sensor and the IMU from the updated geometry.
3. The system of claim 1 , wherein the motion tracking module further provides the poses of the at least one image sensor and the IMU to the rendering module.
4. The system of claim 1 , further comprising the rendering module receiving real-world and virtual content to be rendered as input and combining the real-world and virtual content for concurrent display on the at least one display.
5. The system of claim 4 , further comprising the rendering module using the poses to organize and arrange real-world and virtual objects in a same frame of a video sequence for display on the at least one display.
6. The system of claim 4 , further comprising the rendering module receiving factory calibration data and displaying the real-world and virtual objects according to the calibration data.
7. The system of claim 1 , further comprising an algorithm in the rendering module that adjusts rendering of the augmented reality images on the at least one display using a bending curve model of a real-time geometry of the eyewear device based on the estimated updated geometry of the eyewear device.
8. The system of claim 7 , wherein a bending curve of the bending curve model is at least one of asymmetrical, non-smooth, or uneven.
9. The system of claim 1 , wherein the motion tracking modules comprises at least one of an Extended Kalman Filter (EKF)-driven motion tracking module, an optimization-based module that coordinates spatial relation optimization, or a machine learning-driven module that provides motion tracking.
10. The system of claim 1 , wherein the motion tracking module implements an end-to-end learned approach for tracking and modeling real-time geometry of the eyewear device.
11. The system of claim 1 , wherein the at least one display comprises at least one waveguide and at least one projector.
12. The system of claim 1 , wherein the augmented reality image rendering system is located in at least one of the eyewear device, a mobile computing device, or a server system.
13. A method for displaying augmented reality images on an eyewear device including an inertial measurement unit (IMU) that generates inertial data, at least one image sensor that generates image data, and at least one display for displaying the augmented reality images, wherein the eyewear device has a predetermined geometry defining spatial relations of at least two of the IMU, the at least one image sensor, or the at least one display, comprising:
computing poses of the at least one image sensor and the IMU using at least the image data from the at least one image sensor and the inertial data from the IMU;
computing the predetermined geometry during use of the eyewear device in an augmented reality application;
estimating an updated geometry of the eyewear device from the poses as a result of a geometry change of the eyewear device; and
rendering the augmented reality images including virtual content and real-world objects on the at least one display in accordance with the estimated updated geometry.
14. The method of claim 13 , further comprising receiving real-world and virtual content to be rendered and combining the real-world and virtual content for concurrent display on the at least one display.
15. The method of claim 14 , further comprising organizing and arranging real-world and virtual objects in a same frame of a video sequence for display on the at least one display using the poses.
16. The method of claim 14 , further comprising receiving factory calibration data and displaying the real-world and virtual objects according to the calibration data.
17. The method of claim 13 , further comprising adjusting rendering of the augmented reality images on the at least one display using a bending curve model of a real-time geometry of the eyewear device based on the estimated updated geometry of the eyewear device.
18. The method of claim 17 , wherein a bending curve of the bending curve model is at least one of asymmetrical, non-smooth, or uneven.
19. The method of claim 13 , wherein estimating an updated geometry of the eyewear device from the poses as a result of a geometry change of the eyewear device comprises at least one of:
providing motion tracking of the IMU, the at least one image sensor, and the at least one display using at least one of an Extended Kalman Filter (EKF)-driven motion tracking module, an optimization-based module that coordinates spatial relation optimization, or a machine learning-driven module that provides motion tracking;
implementing an end-to-end learned approach for tracking and modeling a real-time geometry of the eyewear device; or
receiving and processing at least one of inertial data from the IMU or image data from the at least one image sensor to track motion of the JIM, the at least one image sensor, and the at least one display with respect to each other.
20. A non-transitory computer-readable medium comprising instructions stored therein that, when executed by one or more processors, cause the one or more processors to display augmented reality images on an eyewear device including an inertial measurement unit (IMU) that generates inertial data, at least one image sensor that generates image data, and at least one display for displaying the augmented reality images, wherein the eyewear device has a predetermined geometry defining spatial relations of at least two of the IMU, the at least one image sensor, or the at least one display, by performing operations comprising:
computing poses of the at least one image sensor and the IMU using at least the image data from the at least one image sensor and the inertial data from the IMU;
computing the predetermined geometry during use of the eyewear device in an augmented reality application;
estimating an updated geometry of the eyewear device from the poses as a result of a geometry change of the eyewear device; and
rendering the augmented reality images including virtual content and real-world objects on the at least one display in accordance with the estimated updated geometry.